Abstract
In order to solve the problem of how to find out the required information quickly from a large number of reading texts, this paper constructs an intelligent reading model. The model adopts the principle of "the minority obeys the majority". The results of the classifier trained by the three algorithms, those are decision tree, Bagging and Gauss Bayes algorithm, are filtered to build an intelligent reading model. Based on the experimental results, the objective evaluation results of the new combinatorial algorithm are attained.